Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4063 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.4471. Min Range: -5.4471

Max Act: 5.4471. Min Act: -0.0000

Data Index: 848400 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 5.4471. Min Range: -5.4471

Max Act: 4.6689. Min Act: -0.0000

Data Index: 1353703 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 5.4471. Min Range: -5.4471

Max Act: 4.1529. Min Act: -0.0000

Data Index: 347938 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 5.4471. Min Range: -5.4471

Max Act: 4.4541. Min Act: -0.0000

Data Index: 946184 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.9336. Min Act: -0.0000

Data Index: 1147674 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 5.4471. Min Range: -5.4471

Max Act: 4.7868. Min Act: -0.0000

Data Index: 1343517 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 5.4471. Min Range: -5.4471

Max Act: 4.3613. Min Act: -0.0000

Data Index: 643748 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.5996. Min Act: -0.0000

Data Index: 232016 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.4035. Min Act: -0.0000

Data Index: 135672 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.5459. Min Act: -0.0000

Data Index: 3475 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 5.4471. Min Range: -5.4471

Max Act: 4.2037. Min Act: -0.0000

Data Index: 971982 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 5.4471. Min Range: -5.4471

Max Act: 2.8611. Min Act: -0.0000

Data Index: 154302 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.0360. Min Act: -0.0000

Data Index: 304584 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.4176. Min Act: -0.0000

Data Index: 162900 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 5.4471. Min Range: -5.4471

Max Act: 3.0284. Min Act: -0.0000

Data Index: 1295853 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 5.4471. Min Range: -5.4471

Max Act: 2.4935. Min Act: -0.0000

Data Index: 324423 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 5.4471. Min Range: -5.4471

Max Act: 2.5834. Min Act: -0.0000

Data Index: 1035153 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 5.4471. Min Range: -5.4471

Max Act: 2.2527. Min Act: -0.0000

Data Index: 466880 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.4471. Min Range: -5.4471

Max Act: 2.3177. Min Act: -0.0000

Data Index: 820745 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 5.4471. Min Range: -5.4471

Max Act: 2.7645. Min Act: -0.0000

Data Index: 1358818 (C4 (Web Text))

Max Activating Token Index: 1011